About
Research & Development
Improving Multimodal AI with Human-Like Visual Reasoning
TLDR: HuLiRAG is a new framework that enables Multimodal Large Language Models (MLLMs) to understand images in a human-like way for visual question answering....
Research & Development
AnimaRL: A Data-Driven Simulator for Multi-Animal Behavior with Unknown Dynamics
TLDR: AnimaRL is a new data-driven simulator that uses deep reinforcement learning (RL) to model and reproduce complex multi-animal behaviors, even when their underlying...
Research & Development
General Language Models Show Promise in Extracting Medical Orders from Doctor-Patient Conversations
TLDR: The MasonNLP team at MEDIQA-OE 2025 demonstrated that large, general-purpose language models (LLaMA-4 17B), without domain-specific fine-tuning, can effectively extract structured medical orders...
Research & Development
Vision-Language Models Achieve Self-Improvement Through a Novel Consistency Framework
TLDR: Researchers have developed a new framework called 'Triangular Consistency' that allows Vision-Language Models (VLMs) to autonomously generate high-quality training data and refine themselves...
Research & Development
Beyond Group Data: AI Framework Delivers Individualized Sports Motion Guidance
TLDR: The Personalized Motion Guidance Framework (PMGF) uses generative AI, specifically a Transformer-based Variational Autoencoder, to create individualized motion refinement guides for athletes. It...
Research & Development
Decoding the Road: How Align2Act Brings Human Logic to Self-Driving Cars
TLDR: Align2Act is a new autonomous driving framework that uses instruction-tuned large language models (LLMs) to create interpretable and human-aligned motion plans. It breaks...